Alibaba (Qwen) · Released Jul 28, 2025Qwen3 30B-A3B Instruct 2507
Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use.
- Capability
- 137.3ECI · #124 of 165
- Input
- $0.10per 1M tokens
- Output
- $0.30per 1M tokens
- Context
- 262K16K max output
What it costs
- Input
- $0.10per million tokens
- Output
- $0.30per million tokens
- Blended (3:1)
- $0.15cheaper than 82% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.35 |
| Team assistant25M input + 5M output tokens | $4.00 |
| Production app250M input + 50M output tokens | $40.00 |
Median of 12 paid API providers on models.dev.
Independent benchmarks
#124 of 165 scored models
The shaded band is Epoch AI’s confidence range (131.7–139.4); the tick marks the median scored model.
Scores from Epoch AI, run independently of Alibaba (Qwen).
The details
- Lab
- Alibaba (Qwen)
- Released
- Jul 28, 2025
- Context window
- 262,144 tokens
- Max output
- 16,384 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights · Apache 2.0
- Availability
- 14 API providerslisted on models.dev
More from Alibaba (Qwen)
About Qwen3 30B-A3B Instruct 2507
How much does Qwen3 30B-A3B Instruct 2507 cost?
Qwen3 30B-A3B Instruct 2507 costs $0.10 input / $0.30 output per million tokens (median across 12 API providers). At a 3:1 input-to-output mix that is $0.15 per million tokens, cheaper than 82% of the 445 priced models we track.
What is the context window of Qwen3 30B-A3B Instruct 2507?
Qwen3 30B-A3B Instruct 2507 accepts up to 262,144 tokens per request and can write up to 16,384 tokens in one response.
How good is Qwen3 30B-A3B Instruct 2507?
Epoch AI gives Qwen3 30B-A3B Instruct 2507 a Capabilities Index score of 137.3 (likely range 131.7–139.4), ranking it #124 of 165 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 55.6%, OTIS Mock AIME 2024–2025 62.2%.
Is Qwen3 30B-A3B Instruct 2507 open source?
Yes. Alibaba (Qwen) publishes the weights under the Apache 2.0 licence, so it can be downloaded and self-hosted.
What inputs does Qwen3 30B-A3B Instruct 2507 support?
Qwen3 30B-A3B Instruct 2507 accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Qwen3 30B-A3B Instruct 2507 released?
Alibaba (Qwen) released Qwen3 30B-A3B Instruct 2507 on Jul 28, 2025.
What are the best alternatives to Qwen3 30B-A3B Instruct 2507?
The closest current models from other labs on capability, price and release date are GPT OSS 20B (OpenAI, ECI 137.8, $0.07 / $0.25), Gemini 2.5 Flash-Lite Preview 06-17 (Google, ECI 133.8, $0.12 / $0.48), DeepSeek-V3.1 (DeepSeek, ECI 139.8, $0.27 / $1.00) and Llama 4 Maverick 17B Instruct (Meta, ECI 132.3, $0.245 / $0.838).